{"id":4329,"date":"2026-06-25T10:30:16","date_gmt":"2026-06-25T14:30:16","guid":{"rendered":"https:\/\/blogs.mathworks.com\/matlab\/?p=4329"},"modified":"2026-06-25T10:30:16","modified_gmt":"2026-06-25T14:30:16","slug":"from-whiteboard-sketch-to-pareto-front-using-symbolic-math-skills-in-the-agentic-ai-playground","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/matlab\/2026\/06\/25\/from-whiteboard-sketch-to-pareto-front-using-symbolic-math-skills-in-the-agentic-ai-playground\/","title":{"rendered":"From Whiteboard Sketch to Pareto Front: Using Symbolic Math Skills in the Agentic AI Playground"},"content":{"rendered":"
Bio<\/span>: Today's guest blogger is <\/span>Jack Erickson<\/span><\/a>. Jack is a product manager for Symbolic Math Toolbox and <\/span>Quantum Computing at MathWorks<\/span><\/a>. He was previously in AI software developer marketing at Intel.<\/span><\/div>
Engineers communicate in diagrams; from sketches on whiteboards and circuits in textbooks to control loops in notebooks and beyond. What if you could turn a diagram into closed-form analysis and exploration in MATLAB, starting your new projects from first principles?<\/span><\/div>
The recently-launched <\/span>MATLAB Agentic Toolkit<\/span><\/a> pairs the power of MATLAB with your AI agents and coding assistants. Many of the foundation models powering these tools also have multi-modal vision-language capabilities, encoding visual concepts as tokens that can be processed together with language tokens to understand an image. Since many engineers and scientists start projects by manually coding equations from a diagram, sketch, research paper, or textbook, we have used GenAI to make it easier to use these as a starting point to leverage the capabilities of <\/span>Symbolic Math Toolbox<\/span><\/a>.<\/span><\/div>
We have published Symbolic Math Toolbox skill\u202fv1.0 in the <\/span>Agent Skills Playground<\/span><\/a>, which is an experimental repository for prototyping and demonstrating Agent Skills for MATLAB and Simulink work. The repo README explains how to <\/span>install a single skill<\/span><\/a>.<\/span><\/div>
The matlab-symbolic-math skill covers the basic nuances of defining, assigning, and manipulating symbolic variables and equations. It includes hierarchical skills for specific workflows and tasks, such as deriving transfer functions, converting to state-space equations, using variable-precision arithmetic (<\/span>VPA<\/span><\/a>), and <\/span>generating MATLAB functions<\/span><\/a> for numerical analysis in engineering workflows. You can even use these skills together with natural language prompts to learn how to get started with Symbolic Math Toolbox best practices.<\/span><\/div>

Symbolic Code Generation with Agentic AI<\/span><\/h3>
For the task at hand, I drew a simple PI control loop on my whiteboard:<\/span><\/div>
\"\"<\/img><\/div>
I apologize if you can\u2019t read my handwriting, I often struggle to read it as well, but most vision-language models can figure it out. Anyway, here is what the blocks encode:<\/span><\/div>